Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    durations or lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Steele
    0.38
    羯
    0.38
     Jules
    0.36
    EnglishMarks
    0.36
     Karite
    0.35
    няется
    0.35
    បង្
    0.35
     couvertures
    0.34
    ඹ
    0.34
    гая
    0.33
    POSITIVE LOGITS
     concise
    0.50
     ৩
    0.47
     корот
    0.44
     pendek
    0.43
     ۳
    0.42
    trab
    0.42
     succinct
    0.42
    ၃
    0.41
     तीन
    0.41
    3
    0.41
    Act Density 0.002%

    No Known Activations